There is no consensus on how to construct structural brain networks from diffusion MRI and how variations in pre-processing steps affect network reliability and its ability to distinguish subjects. In our MICCAI 2017 paper 'Evaluating 35 Methods to Generate Structural Connectomes Using Pairwise Classification', we addressed this issue by comparing 35 structural connectome-building pipelines. We varied diffusion reconstruction models, tractography algorithms, and parcellations. Next, we classified structural connectome pairs as either belonging to the same individual or not. Connectome weights and eight topological derivative measures formed our feature sets. For experiments, we used three test-retest datasets from the Consortium for Reliability and Reproducibility (CoRR) comprised of a total of 105 individuals. We also compare pairwise classification results to a commonly used parametric test-retest measure, Intraclass Correlation Coefficient (ICC). Machine learning code and full results can be found in the GitHub Repository .